This repo is developed for Strong Baseline For Vehicle Re-Identification in Track 2 Ai-City-2021 Challenges

Last update: Dec 29, 2022

Related tags

Deep Learning track2_aicity_2021

Overview

A STRONG BASELINE FOR VEHICLE RE-IDENTIFICATION

This paper is accepted to the IEEE Conference on Computer Vision and Pattern Recognition Workshop(CVPRW) 2021

This repo is the official implementation for the paper A Strong Baseline For Vehicle Re-Identification in Track 2, 2021 AI CITY CHALLENGE.

I.INTRODUCTION

Our proposed method sheds light on three main factors that contribute most to the performance, including:

Minizing the gap between real and synthetic data
Network modification by stacking multi heads with attention mechanism to backbone
Adaptive loss weight adjustment.

Our method achieves 61.34% mAP on the private CityFlow testset without using external dataset or pseudo labeling, and outperforms all previous works at 87.1% mAP on the Veri benchmark.

II. INSTALLATION

pytorch>=1.2.0
yacs
apex (optional for FP16 training, if you don't have apex installed, please turn-off FP16 training by setting SOLVER.FP16=False)

$ git clone https://github.com/NVIDIA/apex
$ cd apex
$ pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

python>=3.7
cv2

III. REPRODUCE THE RESULT ON AICITY 2020 CHALLENGE

Download the pretrained checkpoint resnext101_ibn

1.Train

Vehicle ReID

    ./scripts/train.sh

Orientation ReID

    ./scripts/ReOriID.sh

Camera ReID

    ./scripts/ReCamID.sh

2. Test

    ./scripts/test.sh

IV. PERFORMANCE

1. Comparison with state-of-the art methods on VeRi776

Download the checkpoint

Comments

The link of [checkpoint] are broken.
Hi, I want to download the checkpoint, but the google link are broken. Could you update link? Thanks.

Comparison with state-of-the art methods on VeRi776 Download the checkpoint
opened by 402650294 2
Train result

excuse me, I train the model by myself base on the default veri.yml setting: backbone ResNeXt101 ibn a, multi-head, CE and SupCon losses, MALW and imagenet pretrained, but only reach 70% mAP, Is my parameter not set correctly?

opened by Kim-Z 0
veri776

I trained on veri. Why hasn't it worked? The accuracy rate hasn't been improved. I only modified the data set of the source code and the path of the pre training model. I hope to get an answer. Thank you!

opened by CarrieYpi 1
Could you offer the feat_distmat.npy file of camera and orientation?
Thanks for your work. And I have a question which is how to get the camera and orientation dismat, after reading your paper and VOC(Vehicle-Orientation-Camera) paper, I only find from VehicleX to get the dismat, but how to get the two files? I can not find the generated codes. Or could your offer the two file? Thanks a lot.

ori_dist = np.load('./output/aicity20/0409-ensemble/ReOriID/feat_distmat.npy')
opened by starstarb 1
tools/train.py

Hello I'm trying to run the code that the paper provided.But I get the error in line 16 in tools/train.py(ModuleNotFoundError: No module named 'lib.config'). Can someone help me?

opened by zooooooly 0
released checkpoint: veri_871.pth's results
Hi, Thank you for your released code! I have some questions when testing with the released veri_871.pth.

When tested without post-processing technique, I got mAP=78.7%;

I can get the reported mAP 87.1% when using re-rank technique. But I thought it was clarified in the paper that non post-processing was used. "For a fair comparison, we only use single model, including backbone ResNeXt101 ibn a, multihead, CE and SupCon losses and MALW without applying pos-processing technique and synthetic data. We achieve the state-of-the-art performance with a large margin compared to previous works" (sec 4.4)

Also I have reproduced the VOC-ReID repo: res50_ibn_a, which got the results on veri-776: 81.5% (w/o re-rank); 87.5% (with re-rank). It seems that larger backbone / multihead / MALW do not brought bonus here? If I have any misunderstandings, please help me to point out. Thank you very much. Attached are the testing logs. voc_reid_test_with_rerank.txt veri_871_test_with_rerank.txt
opened by jiaohere 4

Owner

Cybercore Co. Ltd

GitHub

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones Code

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones Requirements Python 3.8 or later with all requirements.txt dependencies installed,

88 Dec 12, 2022

[ICCV 2021] A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation

45 Dec 12, 2022

🏆 The 1st Place Submission to AICity Challenge 2021 Natural Language-Based Vehicle Retrieval Track (Alibaba-UTS submission)

AI City 2021: Connecting Language and Vision for Natural Language-Based Vehicle Retrieval ?? The 1st Place Submission to AICity Challenge 2021 Natural

82 Dec 29, 2022

Code reproduce for paper "Vehicle Re-identification with Viewpoint-aware Metric Learning"

VANET Code reproduce for paper "Vehicle Re-identification with Viewpoint-aware Metric Learning" Introduction This is the implementation of article VAN

23 Dec 26, 2022

Vehicle direction identification consists of three module detection , tracking and direction recognization.

Vehicle-direction-identification Vehicle direction identification consists of three module detection , tracking and direction recognization. Algorithm

5 Nov 15, 2022

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps[AAAI2021]

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps Here is the code for ssbassline model. We also provide OCR results/features/mode

51 Nov 18, 2022

A Strong Baseline for Image Semantic Segmentation

A Strong Baseline for Image Semantic Segmentation Introduction This project is an open source semantic segmentation toolbox based on PyTorch. It is ba

49 Sep 20, 2022

A tiny, friendly, strong baseline code for Person-reID (based on pytorch).

Pytorch ReID Strong, Small, Friendly A tiny, friendly, strong baseline code for Person-reID (based on pytorch). Strong. It is consistent with the new

3.5k Jan 8, 2023

Image-retrieval-baseline - MUGE Multimodal Retrieval Baseline

MUGE Multimodal Retrieval Baseline This repo is implemented based on the open_cl

47 Dec 16, 2022

Image-generation-baseline - MUGE Text To Image Generation Baseline

MUGE Text To Image Generation Baseline Requirements and Installation More detail

23 Oct 17, 2022

Jingju baseline - A baseline model of our project of Beijing opera script generation

Jingju Baseline It is a baseline of our project about Beijing opera script gener

1 Jan 14, 2022

This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

TransUNet This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation Usage

1.4k Jan 4, 2023

Repo for "Event-Stream Representation for Human Gaits Identification Using Deep Neural Networks"

Summary This is the code for the paper Event-Stream Representation for Human Gaits Identification Using Deep Neural Networks by Yanxiang Wang, Xian Zh

54 Jan 3, 2023

Code for "FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection", ICRA 2021

FGR This repository contains the python implementation for paper "FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection"(I

31 Dec 8, 2022

The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".

Code for "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval" (ACL 2021, Long) This is the repository for baseline m

25 Oct 30, 2022

Official project website for the CVPR 2021 paper "Exploring intermediate representation for monocular vehicle pose estimation"

EgoNet Official project website for the CVPR 2021 paper "Exploring intermediate representation for monocular vehicle pose estimation". This repo inclu

138 Dec 9, 2022